Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3999 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.1493. Min Act: -0.0000

Data Index: 669485 (The Pile)

Max Activating Token Index: 265

Text #1

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1253776 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.6303. Min Act: -0.0000

Data Index: 100424 (The Pile)

Max Activating Token Index: 714

Text #3

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8863. Min Act: -0.0000

Data Index: 195065 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8593. Min Act: -0.0000

Data Index: 489603 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8755. Min Act: -0.0000

Data Index: 5188 (The Pile)

Max Activating Token Index: 424

Text #6

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1782119 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1149590 (The Pile)

Max Activating Token Index: 504

Text #8

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8363. Min Act: -0.0000

Data Index: 171529 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1679182 (The Pile)

Max Activating Token Index: 625

Text #10

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1053928 (The Pile)

Max Activating Token Index: 319

Text #11

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1577387 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7795. Min Act: -0.0000

Data Index: 365226 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8206. Min Act: -0.0000

Data Index: 275830 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7950. Min Act: 0.0000

Data Index: 1699662 (The Pile)

Max Activating Token Index: 431

Text #15

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1488021 (The Pile)

Max Activating Token Index: 776

Text #16

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1913233 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1880386 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7218. Min Act: -0.0000

Data Index: 231716 (The Pile)

Max Activating Token Index: 474

Text #19

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.7802. Min Act: -0.0000

Data Index: 836869 (The Pile)

Max Activating Token Index: 348